aftgee (version 0.3-5)

aftgee: Accelerate Failure Time with Generalize Estimating Equation

Description

A package that uses Generalized Estimating Equations (GEE) to estimate Multivariate Accelerated Failure Time Model (AFT). This package allows dependence working correlation structure for GEE. Moreover, it gives two options of initial estimator, the simple linear regression and the smooth-hegan weight estimator.

Usage

aftgee(formula, data, subset, id,
       weight = NULL,
       margin  = NULL,
       corstr = "independence",
       contrasts = NULL,
       M = 100,
       initial = "lm",
       lsonly = TRUE, 
       iterate = TRUE,
       variance = "ISMB",
       iterMethod = "resampling",
       res = TRUE,
       control = aftgee.control())

Arguments

formula

A formula expression as for glm, of the form response ~ predictors. Response can be in class of survival data. See the documentation of lm, coxph and formula for details.

id

A vector which identifies the clusters. The length of 'id' should be the same as the number of observations.

data

An optional data frame in which to interpret the variables occurring in the formula, along with the id.

subset

An optional vector specifying a subset of observations to be used in the fitting process.

corstr

a character string specifying the correlation structure. The following are permitted: 'independence', 'exchangeable', 'ar1', 'unstructured', 'userdefined', and

M

is the sample size for resampling estimation of the variance

contrasts

an optional list.

initial

a character string specifying the initial estimator. The following are permitted: "lm" for simple linear regression, "srrgehan" for smoothed gehan weight estimator.

lsonly

determine whether to compute variance for initial value

weight

is a weight vector for covariates; default at 1.

iterate

determine whether the iterative procedure is processed when smoothgehan is chosen; default at TRUE.

variance

a character string specifying the covariance estimating method. The following are permitted: 'MB': multipiler resmapling, 'ZLCF': Zeng and Lin's approach with closed form Si, 'ZLMB'

iterMethod

iterating precedure method

margin

a sformula vector; default at 1.

res

Default at TRUE. Value is TRUE if the second moment of the residual life is used to estimate the variance.

control

Controls maxiter and tolerance.

Value

• An object of class "aftgee" representing the fit. An object of class "aftgee" is a list containing at elast the following components:
• coefficients
  a vector of initial value and a vector of point estimates
• coef.res
  a vector of point estimates
• var.res
  estimated covariance matrix
• coef.init
  a vector of initial value
• var.init.mat
  estimated initial covariance matrix
• initial
  a character string specifying the initial estimator.
• conv
  An integer code indicating type of convergence after GEE iteration. 0 indicates successful convergence; 1 indicates that the iteration limit maxit has been reached
• ini.conv
  An integer code indicating type of convergence for initial value. 0 indicates successful convergence; 1 indicates that the iteration limit maxit has been reached
• conv.step
  An integer code indicating the step until convergence

Details

ll{ Package: aftgee Type: Package Version: 0.2-19 Date: 2012-03-12 License: GPL (>=3) LazyLoad: yes }

References

Chiou, S. H. and Kim, H. and Yan, J. (2012) Semiparametric Multivariate Accelerated Failure Time Model with Generalized Estimating Equations. University of Connecticut. Jin, Z. and Lin, D. Y. and Ying, Z. (2006) On Least-squares Regression with Censored Data. Biometrika, 90, 341--353. Johnson, L. M. and Strawderman, R. L. (2009) Induced Smoothing for the Semiparametric Accelerated Failure Time Model: Asymptotics and Extensions to Clustered Data. Biometrika, 96, 577-590.

Examples

data(kidney)
fit <- aftgee(Surv(time, status) ~ age + sex, id = id, data = kidney, initial = "srrgehan")
fit
summary(fit)

####################################################################
## set.seed(12)
## x1 <- rnorm(400)
## x2 <- runif(400)
## e1 <- rnorm(100, sd = 1)
## e2 <- rnorm(100, sd = 2)
## e3 <- rnorm(100, sd = 3)
## e4 <- rnorm(100, sd = 4)
## id <- rep(1:100, each = 4)
## e <- as.vector(rbind(e1, e2, e3, e4))
## marg <- rep(1:4, 100)
## time <- exp(2 - x1 + 2 * x2 + e)
## x <- as.matrix(cbind(x1, x2))
## c <- runif(400, 0, 10)
## delta <- (time < c) * 1
## y <- pmin(time, c)
## foo <- aftgee(Surv(y, delta) ~ x, id = id, initial = "srrgehan", M=1)
## foo2 <- aftgee(Surv(y, delta) ~ x, id = id, initial = "srrgehan", margin = marg, res = FALSE, M=50)
## foo3 <- aftgee(Surv(y, delta) ~ x, id = id, initial = "srrgehan", margin = marg, res = TRUE, M=50)
## summary(foo)
## summary(foo2)
## summary(foo3)
## cbind(foo$aft.fit, foo2$aft.fit, foo3$aft.fit)